11 accepted papers
Random frame-level data missing is a critical challenge in multimodal sentiment analysis. Existing methods are largely limited to passive completion via single-pass feedforward connections and static cross-modal fusion, which struggle to generate high-quality completed features. However, the brain i
Studies have shown that catastrophic forgetting primarily stems from the difficulty of reactivating old memories; although parameter-efficient fine-tuning can mitigate forgetting while keeping most model parameters frozen, it still falls short in fully reawakening knowledge of prior tasks. In contra…
Abstract visual reasoning benchmarks such as ARC-AGI evaluate the ability to infer generalizable transformation rules from few graphical demonstrations, a capability where current deep learning models severely underperform. Mainstream LLMs achieve only 15.8% (DeepSeek-R1) and 34.5% (o3-mini-high) ac
Prompt learning has recently emerged as a novel, parameter-efficient paradigm to tackle the missing modalities challenge. However, existing prompting methods often overlook the internal structural information within prompt vectors, limiting their effectiveness in guiding frozen backbone models under…
Open-world reinforcement learning challenges agents to develop intelligent behavior in vast exploration spaces. Recent approaches like LS-Imagine have advanced the field by extending imagination horizons through jumpy state transitions, yet remain limited by fixed exploration mechanisms and static j…
Conventional image set methods typically learn from image sets stored in a single location. However, in real-world applications, image sets are often distributed across different locations. Learning from such distributed sets using deep neural networks poses challenges for efficient image set classi
Motion planning in high-dimensional continuous spaces remains challenging due to complex environments and computational constraints. Although learning-based planners, especially graph neural network (GNN)-based, have significantly improved planning performance, they still struggle with inaccurate gr…
Cross-sensory interaction is a key aspect for multisensory recognition. Without cross-sensory interaction, artificial neural networks show inferior performance in multisensory recognition. On the contrary, the human brain has an inherently remarkable ability in multisensory recognition, which stems…
This paper presents a novel end-to-end dynamic time-lapse video generation framework, named DTVNet, to generate diversified time-lapse videos from a single landscape image, which are conditioned on normalized motion vectors. The proposed DTVNet consists of two submodules: mph{Optical Flow Encoder} (…
A common drawback of the EEG applications is that the volume conduction of human head leads to lots of redundant information in EEG recordings. To reduce the redundancy and choose informative EEG features, in this paper, we propose an EEG feature selection technique, termed as Feature Selection with…
Various supervised embedded methods have been proposed to select discriminative features from original ones, such as Feature Selection with Orthogonal Regression (FSOR) and Robust Feature Selection. Compared with embedded methods based on the least square regression, FSOR, utilizing orthogonal regre…